Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    nothing much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puedan
    0.37
     পারবে
    0.37
    Notice
    0.36
    atts
    0.36
    despite
    0.36
    NOTE
    0.35
     soften
    0.35
    Note
    0.34
    Kindly
    0.34
     رغم
    0.33
    POSITIVE LOGITS
     nothing
    0.70
    没什么
    0.70
     dunno
    0.68
     ничего
    0.68
     semplicemente
    0.67
     mostly
    0.66
     просто
    0.63
     gewoon
    0.62
     nada
    0.61
     ništa
    0.61
    Act Density 0.014%

    No Known Activations